The Fraud Detection Optimization in Open Metaverse Blockchain Transactions: Case study based on ML-GRU Neural Networks

The study explores anomaly detection in blockchain transactions within the Open Metaverse Our proposed system aims to achieve three critical objectives: detecting fraudulent transactions by identifying suspicious patterns and anomalies, assessing transaction risks through the categorization of risk profiles, and analyzing user behavior to enhance security, personalize financial services, and improve user experiences. Through the meticulous classification of transactions for fraud detection, risk assessment, and user behavior analysis, this project aspires to bolster the security and transparency of Open Metaverse finance, setting the stage for a safer and more user-centric virtual financial landscape. DATASET: -The dataset comprises 78,600 entries, each depicting a transaction within the metaverse. These entries are characterized by various attributes including the Timestamp, Hour of the Day, Sending and Receiving Addresses, Transaction Amount, Type, Location Region, and IP Prefix, along with user-centric data like Login Frequency, Session Duration, Purchase Patterns, Age Group, Risk Score, and potential Anomalies.